| 摘要 |
This invention relates to a method and apparatus for computer generated voice in an interactive voice response system (IVR). A user will normally be able to identify the pre-recorded segments from the synthesized ones played by the IVR. According to an aspect of the invention there is provided a method of processing voice prompts in an IVR. The method can include: identifying a set of voice prompts within an application for output in a single voice, the set having a pre-recorded voice prompt and a computer generated voice prompt; providing reference voice characteristics formed from the pre-recorded voice prompt; and playing the computer generated voice prompt using the reference voice characteristics whereby the computer generated voice prompt sounds like the pre-recorded voice prompt. |
